Image recognition method and device
An image recognition and image technology, applied in the field of image processing, can solve problems such as poor image recognition efficiency
Active Publication Date: 2021-10-01
BOE TECH GRP CO LTD
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] For this reason, the first object of the present invention is to propose an image recognition method for solving the problem of poor image recognition efficiency in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0060] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.
[0061] The image recognition method and device according to the embodiments of the present invention will be described below with reference to the accompanying drawings.
[0062] figure 1 It is a schematic flowchart of an image recognition method provided by an embodiment of the present invention. Such as figure 1 As shown, the image recognition method includes the following steps:
[0063] S101. Acquire an image to be recognized.
[0064] The execution body of the image recognition method provided by the present invention is...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention proposes an image recognition method and device, wherein the method includes: obtaining an image to be recognized; inputting the image into the first preset block of the residual neural network, obtaining the first image feature corresponding to the image; inputting the first image feature The second preset block of the residual neural network, the attention model, the first convolutional layer and the pooling layer are arranged in order to obtain the characteristic image features with position representation and channel representation, and the corresponding first label information; the second An image feature is input into the second convolutional layer and the bidirectional neural network arranged in sequence to obtain the second label information with label correlation representation; according to the first label information and the second label information, determine the label information corresponding to the image, so as to be able to combine The positional relationship and correlation between the tags are used to perform multi-label recognition on the image, which can accurately identify multiple tags in the image and improve the efficiency of image recognition.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to an image recognition method and device. Background technique [0002] The current image recognition method, when performing multi-label recognition, regards each label as independent and irrelevant to each other, and recognizes each label separately, while the multi-label images generally have a fixed positional relationship and Correlation, for example, the "sky" label is generally above the image, and the "grassland" label is generally below the image, and the correlation between the "sky" label and the "white cloud" label is relatively large, and they often appear at the same time. However, the above-mentioned image recognition method does not involve the positional relationship and correlation between tags when performing multi-tag recognition, so it is difficult to accurately recognize multiple tags in the image, and the image recognition efficiency is poor....
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/04G06V10/764G06V10/774G06V10/776
CPCG06N3/08G06V10/454G06V10/82G06V10/776G06V10/764G06V10/774G06N3/044G06N3/045G06N20/00G06F18/214G06F2218/00
Inventor 王婷婷李月
Owner BOE TECH GRP CO LTD